v0.5.4

NewPromt
- small fix

word2md/classify.py

@@ -26,7 +26,8 @@ APPENDIX_RE = re.compile(
 )
 NUMBERED_HEADING_RE = re.compile(r"^(\d+(?:\.\d+)*)\.?\s+(.+)$")
 PRACTICE_RE = re.compile(r"^Практическая\s+работа\b", re.IGNORECASE)
-LIST_MARKER_RE = re.compile(r"^(?:[–—\-•▪]|(\d+)\.)\s*\t?\s*(.*)$")
+LIST_MARKER_RE = re.compile(r"^(?:[–—\-•▪]|(\d+(?:\.\d+)*)\.)\s*\t?\s*(.*)$")
+ORDERED_MARKER_RE = re.compile(r"^(\d+(?:\.\d+)*)\.\s*\t?\s*(.+)$")
 BIBLIO_LINE_RE = re.compile(r"^\[(\d+(?:\.\d+)?)\]\s*[:.]?\s*(.+)$")
 BODY_START_TITLES = SPECIAL_UPPER | {"СОДЕРЖАНИЕ"}
 
@@ -136,23 +137,37 @@ def classify_heading_text(text: str, style_level: int | None) -> tuple[int, str,
     return level, raw, True
 
 
-def look_like_list_item(text: str) -> tuple[bool, bool, str] | None:
+def parse_list_item(text: str) -> tuple[bool, int, str] | None:
     """
-    Detect md2gost-style list lines (–\\t / 1.\\t) or plain markers.
-    Returns (ordered, marker_ok, body) or None.
+    Detect md2gost-style list lines (–\\t / 1.\\t / 1.1.\\t).
+    Returns (ordered, level, body) or None.
     """
     t = (text or "").strip()
     if not t:
         return None
     if t[0] in ("–", "—", "-", "•", "▪") and (len(t) == 1 or t[1] in "\t "):
         body = t[1:].lstrip("\t ").strip()
-        return False, True, body
-    m = re.match(r"^(\d+)\.\s*\t?\s*(.+)$", t)
+        return False, 1, body
+    m = ORDERED_MARKER_RE.match(t)
     if m:
-        return True, True, m.group(2).strip()
+        number = m.group(1)
+        level = number.count(".") + 1
+        return True, level, m.group(2).strip()
     return None
 
 
+def look_like_list_item(text: str) -> tuple[bool, bool, str] | None:
+    """
+    Detect md2gost-style list lines (–\\t / 1.\\t) or plain markers.
+    Returns (ordered, marker_ok, body) or None.
+    """
+    parsed = parse_list_item(text)
+    if parsed is None:
+        return None
+    ordered, _level, body = parsed
+    return ordered, True, body
+
+
 def parse_biblio_line(text: str) -> tuple[str, str] | None:
     m = BIBLIO_LINE_RE.match((text or "").strip())
     if not m: